Llama 3.2 is Meta's open-weight multimodal model family optimized for edge devices, supporting vision-language understanding, on-device text generation, and customizable local deployment.
MMMLU is a large-scale, multilingual, multitask benchmark dataset for rigorously evaluating language models across 14 languages and 57 academic disciplines.
GOT-OCR2.0 is an open-source, multimodal OCR model that converts complex documents—including math, charts, music scores, and multilingual text—into editable Markdown or LaTeX with interactive region control and long-context understanding.
oneWebot2 is a Windows-based, no-code WeChat AI bot package that lets users deploy intelligent chat assistants via a graphical interface and one-click executable — no Python setup required.
SFR-RAG is an open-source, retrieval-augmented language model from Salesforce AI Research that improves factual accuracy, reduces hallucinations, and supports reliable, context-grounded text generation and conversational AI.
V-JEPA is an open-source, self-supervised video foundation model that learns visual representations by predicting masked frame features—enabling robust video understanding without labels.
DiT is an open-source image generation model that replaces convolutional U-Nets with Transformers in diffusion models to produce high-fidelity, scalable, and controllable synthetic images.
ScreenAgent is an open-source AI agent that observes real computer screens and autonomously performs complex desktop tasks using vision-language understanding and reinforcement learning.
OpenCodeInterpreter is an open-source AI coding assistant that generates, executes, and iteratively refines code using large language models and real-time execution feedback.
ChatMusician is an open-source large language model that understands and generates music using text-based notation—enabling composition, theory Q&A, and stylistic imitation without external multimodal components.
StarCoder 2 is an open-weight, high-performance large language model designed specifically for code generation, understanding, and interactive programming assistance across 600+ languages.
TextDiffuser-2 is an open-source text-to-image diffusion model that generates high-fidelity, resolution-flexible images from natural language descriptions.
OmniGen is an open-source unified diffusion model that handles text-to-image generation, image editing, subject-driven synthesis, visual conditioning, and even classic CV tasks—all within a single streamlined architecture.
I2VGen is an open-source image-to-video model by Alibaba DAMO Academy that transforms static images into high-resolution, temporally coherent videos using cascaded diffusion.
eSearch is a free, open-source desktop and web tool that captures screenshots, extracts text via OCR, searches the web, translates content, and performs reverse image search — all in one streamlined workflow.
HivisionIDPhotos is a lightweight, open-source AI tool that generates professional ID photos with automatic matting, background replacement, layout printing, and optional beautification — all running locally on CPU.
WiseFlow is an open-source AI workflow tool that automatically crawls, parses, classifies, and organizes web and social media content—including WeChat articles—using LLMs and statistical learning, all without GPU requirements.
OmniParser is a lightweight, open-source screen parsing module that converts UI screenshots into structured, actionable elements to boost visual-language model performance in GUI-based agent tasks.
Seed-VC is a zero-shot voice cloning model that converts speech to new voices without needing target speaker recordings, hosted as a free Hugging Face Space.